| About this Abstract |
| Meeting |
2025 TMS Annual Meeting & Exhibition
|
| Symposium
|
Novel Strategies for Rapid Acquisition and Processing of Large Datasets from Advanced Characterization Techniques
|
| Presentation Title |
Towards Accelerated Material Characterization: Uncertainty Quantification in Elemental Analysis |
| Author(s) |
Jarred Fountain, Aaron Stebner |
| On-Site Speaker (Planned) |
Jarred Fountain |
| Abstract Scope |
With increasing usage of data-driven material development techniques via integrated computational materials engineering, the realization of accelerated material discovery using self-driving labs seems almost a given in the near future. Elemental analysis plays a key role in this materials discovery however, elemental analysis is currently a bottleneck for most self-driving labs dedicated to material discovery. This is due to the lack of methods for performing autonomous data-driven decision-making required to generate quality results efficiently. We aim to address these issues using a statistical framework for experimental planning that relies on evaluating a cost function that is dependent on uncertainty, price, and time. Our first step in developing this cost function is to predict the uncertainty in a measurement performed on certain spectroscopic systems. |
| Proceedings Inclusion? |
Planned: |
| Keywords |
Machine Learning, Modeling and Simulation, Characterization |